智能体
Agent 规划、多步流程与编排
Bankr Agent - Automation
BankrBot
This skill should be used when the user asks about "limit order", "stop loss", "DCA", "TWAP", "schedule", "automate", "recurring order", "price trigger", "cancel automation", "my automations", or any automated trading operation. Provides guidance on limit orders, scheduled commands, and automated strategies.
ai-data-engineering
ancoleman
Data pipelines, feature stores, and embedding generation for AI/ML systems. Use when building RAG pipelines, ML feature serving, or data transformations. Covers feature stores (Feast, Tecton), embedding pipelines, chunking strategies, orchestration (Dagster, Prefect, Airflow), dbt transformations, data versioning (LakeFS), and experiment tracking (MLflow, W&B).
workflow-enforcer-skill
ScientiaCapital
"Enforces workflow discipline across ALL projects. Ensures Claude checks for specialized agents before responding, announces skill/agent usage, and creates TodoWrite todos for multi-step tasks. Triggers: automatic on all sessions, use the right agent, follow workflow."
agent-teams
ScientiaCapital
"Orchestrate teams of parallel Claude Code sessions working on the same codebase. Handles task decomposition, agent coordination, context isolation, and merge strategies. Builds on worktree-manager for infrastructure."
subagent-teams
ScientiaCapital
"Orchestrate in-session Task tool teams for parallel work. Fan-out research, implementation, review, and documentation across subagents. Use when: parallel tasks, fan-out, subagent team, Task tool, in-session agents."
agent-capability-matrix
ScientiaCapital
"Map task types to the best agent, skill, model, and fallback. Route any task to the right tool. Use when: which agent, route task, agent for this, best agent, capability matrix."
workflow-orchestrator
ScientiaCapital
"Project workflow system - cost tracking, parallel execution, security gates, agent orchestration. Use when: start day, begin session, status check, new feature, build, implement, end day, wrap up, debug, investigate, research, evaluate."
langgraph-agents
ScientiaCapital
"Multi-agent systems with LangGraph - supervisor/swarm patterns, state coordination, multi-provider routing. Use when building multi-agent workflows, coordinating agents, or need cost-optimized orchestration. Uses Claude, DeepSeek, Gemini (no OpenAI)."
clawd-control
Temaki-AI
Monitor and manage your Clawdbot agent fleet from within an agent. Query health, sessions, usage, and trigger actions via the Clawd Control dashboard API.
pasta-attack-sim
florianbuetow
This skill should be used when the user asks to "simulate attacks", "build attack trees", "model exploit chains", "score exploitability", or is running PASTA stage 6. Also triggers when the user asks about attack scenarios, red team simulation, DREAD scoring, or detection gap analysis in a threat modeling context. Part of the PASTA threat modeling methodology (Stage 6 of 7).
tmux
sebnow
"Teaches agents to control tmux sessions for interactive CLIs and long-running processes via the Bash tool. Use when running REPLs, debuggers, database shells, long-running servers, or any tool requiring a persistent TTY. Triggers: 'start a REPL', 'run interactively', 'interactive session', 'long-running process', 'background server', 'keep running'. Do NOT use for simple one-shot commands or non-interactive background tasks that the Bash tool handles natively."
agent-orchestrator-standalone
mrclrchtr
Orchestrate complex work via a phase-gated multi-agent loop (audit → design → implement → review → validate → deliver). Use when you need to split work into subsystems, run independent audits, reconcile findings into a confirmed issue list, delegate fixes in clusters, enforce PASS/FAIL review gates, and drive an end-to-end validated delivery. Do not use for small, single-file tasks.
prompt-engineering
sebnow
"Use when writing or improving any LLM prompts. Applies TDD methodology and research-backed practices (Meincke 2025): test don't assume, measure baseline, iterate rigorously. Prevents assuming universal techniques work. Includes persuasion principles for compliance. Triggers: 'write a prompt', 'improve prompt', 'prompt not working', general prompting, application development."
git-helpers
adeonir
Git workflow helper for conventional commits, confidence-scored code review, and pull request management. Use when: committing changes, reviewing code, creating PRs, generating PR descriptions, analyzing diffs. Triggers on "commit", "review", "push", "create PR", "PR description", "summarize changes".
debug-tools
adeonir
Iterative debugging workflow with confidence scoring and strategic log injection. Five phases: investigate, inject logs, propose fix, verify, cleanup. Use when: debugging unexpected behavior, silent errors, intermittent failures, or issues requiring runtime data. Triggers on "debug", "fix bug", "investigate", "trace issue", "add debug logs", "cleanup debug logs".
vitest
joncrangle
Specialist in Vitest, a blazing fast unit test framework powered by Vite. Focuses on Jest compatibility, in-source testing, and native ESM support.
programming-workflow
cuipengfei
编程工作流 - 统一的测试驱动开发(TDD)工作流程。包含准备、设计、测试实现、代码实现和审查五个阶段。
skill-writing
sebnow
"Creates and edits SKILL.md files for agent skills. Use when building or refining agent configuration. Enforces red-green-refactor methodology with agent-specific requirements: frontmatter format, 500-line limit, progressive disclosure, quality gates. Triggers: 'create a skill', 'write a skill', 'new SKILL.md', 'create agent documentation'. Do NOT use for general documentation or README files."
agent-orchestrator
mrclrchtr
Orchestrate complex work via a phase-gated multi-agent loop (audit → design → implement → review → validate → deliver). Use when you need to split work into subsystems, run independent audits, reconcile findings into a confirmed issue list, delegate fixes in clusters, enforce PASS/FAIL review gates, and drive an end-to-end validated delivery. Do not use for small, single-file tasks.
foundational-principles
cuipengfei
基础原则 - AI 助手的核心思维原则和指令框架概述。包含系统思维、辩证思维、创新思维和批判思维四大核心原则。
cto
jordanhubbard
The ultimate technical decision-maker and default triage authority for
remediation-specialist
jordanhubbard
A meta-level debugging specialist who analyzes stuck agents, identifies systemic blockers, and implements fixes. Acts as Loom's self-healing mechanism.
expert-routing
Harryoung
Domain expert routing. When the knowledge base cannot answer user questions, find and notify the corresponding expert based on the question domain. Only available in IM mode. Trigger condition: No results in 6-stage retrieval.
batch-notification
Harryoung
Send IM messages to users in batch. Used for notifying specific user groups, sending after table filtering, all-staff notifications, etc. Use this Skill when administrators request batch notifications, mass messaging, or notifications after table filtering. Trigger words: notify/send/mass + users/batch/table.